Finki SNZ lab2 zadaca 1

trainingData=[['slashdot','USA','yes',18,'None'],
        ['google','France','yes',23,'Premium'],
        ['google','France','yes',23,'Basic'],
        ['google','France','yes',23,'Basic'],
        ['digg','USA','yes',24,'Basic'],
        ['kiwitobes','France','yes',23,'Basic'],
        ['google','UK','no',21,'Premium'],
        ['(direct)','New Zealand','no',12,'None'],
        ['(direct)','UK','no',21,'Basic'],
        ['google','USA','no',24,'Premium'],
        ['slashdot','France','yes',19,'None'],
        ['digg','USA','no',18,'None'],
        ['google','UK','no',18,'None'],
        ['kiwitobes','UK','no',19,'None'],
        ['digg','New Zealand','yes',12,'Basic'],
        ['slashdot','UK','no',21,'None'],
        ['google','UK','yes',18,'Basic'],
        ['kiwitobes','France','yes',19,'Basic']]
class decisionnode:
    def __init__(self, col=-1,value=None, results=None,tb=None,fb=None,level=0 ):
        self.col=col
        self.value=value
        self.results=results
        self.tb=tb
        self.fb=fb
        self.level=level;

def sporedi_kolona(row, column, value):
    if isinstance(value, int) or isinstance(value,float):
        return row[column]>=value
    else:
        return row[column]==value
    #-----------------------------------------------------------------------
def divideset (rows, column, value):
    split_function=sporedi_kolona
    s1=[]
    s2=[]

    for row in rows:
        if split_function(row,column,value):
            s1.append(row)
        else:
            s2.append(row)
    return (s1,s2)
def uniquecounts (rows):
    results={}
    for row in rows:
        r=row[len(row)-1]
        if r not in results:
            results[r]=0
        results[r]+=1
    return results
def Log2 (x):
    from math import log
    return log(x)/log(2)
def entropy (rows):
    results=uniquecounts(rows)
    ent=0.0
    for key in results.keys():
        p=float(results[key])/len(rows)
        ent=ent-p*Log2(p)

    return ent
def buildtree(br,rows, scoref=entropy):
    if len(rows)==0:return decisionnode()
    current_score=scoref(rows)

    best_gain=0.0
    best_criteria=None
    best_sets=None

    column_count=len(rows[0])-1;
    for col in range(0,column_count):
        column_values={}
        for row in rows:
            column_values[row[col]]=1
        for value in column_values.keys():
            (set1,set2)=divideset(rows,col,value)
            p=float(len(set1))/len(rows)
            gain=current_score-p*scoref(set1)-(1-p)*scoref(set2)
            if gain > best_gain and len(set1) > 0 and len(set2) > 0:
                best_gain = gain
                best_criteria = (col, value)
                best_sets = (set1, set2)
    br=br+1;
    if best_gain > 0:
        trueBranch = buildtree(br, best_sets[0])
        falseBranch = buildtree(br, best_sets[1])
        return decisionnode(col=best_criteria[0], value=best_criteria[1],
                            tb=trueBranch, fb=falseBranch, level=br)
    else:
        return decisionnode(results=uniquecounts(rows), level=br)

def printtree (tree,indent=''):
    if tree.results!=None:
        print str(tree.results)
    else:
        print str(tree.col)+':'+str(tree.value)+'?'+" Level=" + str(tree.level)
        print indent + 'T->',
        printtree(tree.tb, indent + '  ')
        print indent + 'F->',
        printtree(tree.fb, indent + '  ')


if __name__ == "__main__":
    # referrer='slashdot'
    # location='US'
    # readFAQ='no'
    # pagesVisited=19
    # serviceChosen='None'

    referrer=input()
    location=input()
    readFAQ=input()
    pagesVisited=input()
    serviceChosen=input()

    testCase=[referrer, location, readFAQ, pagesVisited, serviceChosen]
    trainingData.append(testCase)
    t=buildtree(-1,trainingData)
    printtree(t)
    #print ("da")